Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location and accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.93
    n
    -0.88
     her
    -0.84
    en
    -0.83
    el
    -0.82
    a
    -0.81
     ‘
    -0.81
    sa
    -0.79
    s
    -0.78
     Pet
    -0.78
    POSITIVE LOGITS
     myſelf
    1.49
     Monfieur
    1.49
     itſelf
    1.47
     Efq
    1.43
     becauſe
    1.43
     purpoſe
    1.35
     himſelf
    1.34
     Anſ
    1.32
     themſelves
    1.32
     auffi
    1.30
    Act Density 0.079%

    No Known Activations